© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7831
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols mixed with Asian characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    24
    +0.14
    0.5%
    517
    +0.12
    0.4%
    447
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.14
    0.01
    275
    +0.12
    0.01
    479
    +0.12
    0.01
    Negative Logits
    oser
    -1.17
    uggest
    -1.03
    entimes
    -1.01
    pec
    -1.01
    uke
    -1.00
    okes
    -1.00
    osing
    -0.99
    augh
    -0.99
    okers
    -0.98
    bro
    -0.97
    POSITIVE LOGITS
     Rivals
    1.02
     Leilan
    0.99
     Carbuncle
    0.93
     Champions
    0.92
     Werewolf
    0.90
    Constructed
    0.90
     Typhoon
    0.89
     Gork
    0.87
    ãĢIJ
    0.87
     Sakura
    0.87
    Activations Density 0.110%

    No Known Activations